Re: [Computer-go] mit-develops-algorithm-to-accelerate-neural-networks-by-200x

2019-03-24 Thread Brian Lee
this doesn't actually speed up the neural networks that much; it's a technique to more quickly brute-force the search space of possible neural networks for ones that execute faster while maintaining similar accuracy. Typical hype article. Anyway, the effort spent looking for bizarre architectures

[Computer-go] mit-develops-algorithm-to-accelerate-neural-networks-by-200x

2019-03-24 Thread Ray Tayek
https://www.extremetech.com/computing/288152-mit-develops-algorithm-to-accelerate-neural-networks-by-200x i wonder how much this would speed up go programs? thanks -- Honesty is a very expensive gift. So, don't expect it from cheap people - Warren Buffett http://tayek.com/

Re: [Computer-go] Hyper-Parameter Sweep on AlphaZero General

2019-03-24 Thread David Wu
Thanks for sharing the link. Taking a brief look at this paper, I'm quite confused about their methodology and their interpretation of their data. For example in figure 2 (b), if I understand correctly, they plot Elo ratings for three independent runs where they run the entire AlphaZero process

[Computer-go] Accelerating Self-Play Learning in Go

2019-03-24 Thread Rémi Coulom
Hi, I have just found out that the list is not sending emails to my free.fr email address any more. So I subscribed with my gmail address, which I hope should work better. I had missed that very interesting message by David Wu (

[Computer-go] Hyper-Parameter Sweep on AlphaZero General

2019-03-24 Thread Rémi Coulom
Hi, Here is a paper you might be interested in: Abstract: Since AlphaGo and AlphaGo Zero have achieved breakground successes in the game of Go, the programs have been generalized to solve other tasks. Subsequently, AlphaZero was developed to play Go, Chess and Shogi. In the literature, the